We explore the use of Swin Transformer V2, a pre-trained vision Transformer, for photometric classification in a multi-survey setting by leveraging light curves from the Zwicky Transient Facility (ZTF) and the Asteroid Terrestrial-impact Last Alert System (ATLAS). We evaluate different strategies for integrating data from these surveys and find that a multi-survey architecture which processes them jointly achieves the best performance. These results highlight the importance of modeling survey-specific characteristics and cross-survey interactions, and provide guidance for building scalable classifiers for future time-domain astronomy.
@article{arxiv.2507.11711,
title = {Image-Based Multi-Survey Classification of Light Curves with a Pre-Trained Vision Transformer},
author = {Daniel Moreno-Cartagena and Guillermo Cabrera-Vives and Alejandra M. Muñoz Arancibia and Pavlos Protopapas and Francisco Förster and Márcio Catelan and A. Bayo and Pablo A. Estévez and P. Sánchez-Sáez and Franz E. Bauer and M. Pavez-Herrera and L. Hernández-García and Gonzalo Rojas},
journal= {arXiv preprint arXiv:2507.11711},
year = {2025}
}
Comments
Accepted at the 2025 Workshop on Machine Learning for Astrophysics at the International Conference on Machine Learning (ICML)